From: Paolo Abeni <[email protected]>
mptcp_cleanup_rbuf() needs to know the last most recent, mptcp-level
rcv_wnd sent, and such information is tracked into the msk->old_wspace
field, updated at ack transmission time by mptcp_write_options().
Fallback socket do not add any mptcp options, such helper is never
invoked, and msk->old_wspace value remain stale. That in turn makes
ack generation at recvmsg() time quite random.
Address the issue ensuring mptcp_write_options() is invoked even for
fallback sockets, and just update the needed info in such a case.
The issue went unnoticed for a long time, as mptcp currently overshots
the fallback socket receive buffer autotune significantly. It is going
to change in the near future.
Fixes: e3859603ba13 ("mptcp: better msk receive window updates")
Cc: [email protected]
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/594
Signed-off-by: Paolo Abeni <[email protected]>
Reviewed-by: Geliang Tang <[email protected]>
Reviewed-by: Matthieu Baerts (NGI0) <[email protected]>
Signed-off-by: Matthieu Baerts (NGI0) <[email protected]>
---
net/mptcp/options.c | 23 ++++++++++++++++++++++-
1 file changed, 22 insertions(+), 1 deletion(-)
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 1103b3341a70..8a63bd00807d 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -838,8 +838,11 @@ bool mptcp_established_options(struct sock *sk, struct
sk_buff *skb,
opts->suboptions = 0;
+ /* Force later mptcp_write_options(), but do not use any actual
+ * option space.
+ */
if (unlikely(__mptcp_check_fallback(msk) &&
!mptcp_check_infinite_map(skb)))
- return false;
+ return true;
if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) {
if (mptcp_established_options_fastclose(sk, &opt_size,
remaining, opts) ||
@@ -1319,6 +1322,20 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct
tcphdr *th)
WRITE_ONCE(msk->old_wspace, tp->rcv_wnd);
}
+static void mptcp_track_rwin(struct tcp_sock *tp)
+{
+ const struct sock *ssk = (const struct sock *)tp;
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_sock *msk;
+
+ if (!ssk)
+ return;
+
+ subflow = mptcp_subflow_ctx(ssk);
+ msk = mptcp_sk(subflow->conn);
+ WRITE_ONCE(msk->old_wspace, tp->rcv_wnd);
+}
+
__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum
sum)
{
struct csum_pseudo_header header;
@@ -1611,6 +1628,10 @@ void mptcp_write_options(struct tcphdr *th, __be32 *ptr,
struct tcp_sock *tp,
opts->reset_transient,
opts->reset_reason);
return;
+ } else if (unlikely(!opts->suboptions)) {
+ /* Fallback to TCP */
+ mptcp_track_rwin(tp);
+ return;
}
if (OPTION_MPTCP_PRIO & opts->suboptions) {
--
2.51.0
